© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17436
    Prev
    Next
    INDEX
    Explanations

    classification criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boarding
    -0.06
    é¢Ħä¼°
    -0.06
     Corpus
    -0.06
     بÛĮÙħ
    -0.06
    -sur
    -0.06
    Å¡ki
    -0.06
     hiá»ĥm
    -0.06
    atte
    -0.06
    çĶ¨äºº
    -0.06
    дни
    -0.06
    POSITIVE LOGITS
     criteria
    0.07
    criteria
    0.06
     Criteria
    0.06
    singular
    0.06
    Criteria
    0.06
    åĨ³å®ļ
    0.06
     singular
    0.05
     criterion
    0.05
     classification
    0.05
    ilight
    0.05
    Activations Density 0.013%

    No Known Activations